LL

Pruned80 Llama 3.2 3B

LlamaGGUF by mikepwcscalingUpdated 2025-02-06
Download on Hugging Face
Parameters610M
Context128K
Layers28
Architecturellama
Smallest quant0.3 GB
Quick answer

Pruned80 Llama 3.2 3B needs about 2.6 GB of memory at Q4_K_M (a 1.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 0.3 GB (Q4_0) to 1.2 GB (Q4_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.

Pruned80 Llama 3.2 3B is a 610M-parameter Llama model in GGUF format, quantized by mikepwcscaling. Its trained context length is 128K tokens. The repository has 3 quant files, from 0.3 GB (Q4_0) to 1.2 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.3 GB 1.8 GB
Fits Get file →
Q8_00.5 GB 1.9 GB
Fits Get file →
Q4_K_M1.2 GB 2.6 GB
Fits Get file →

What GPU do you need for Pruned80 Llama 3.2 3B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q4_K_M (1.2 GB file, about 2.6 GB in use).

Which Pruned80 Llama 3.2 3B quant should you choose?

Q4_K_M is the usual starting point for Pruned80 Llama 3.2 3B: it balances file size and quality well. Here it is a 1.2 GB file.

The Q8_0 file is 0.5 GB, about 0.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q4_0 at 0.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters610M
Layers28
Trained context131,072 tokens
KV cache (fp16)112 KB per token

Source

Quantized bymikepwcscaling
FamilyLlama
Licenseapache-2.0
Downloads (HF)36
Last updated2025-02-06

Frequently asked questions about Pruned80 Llama 3.2 3B

How much VRAM does Pruned80 Llama 3.2 3B need?

About 2.6 GB at Q4_K_M with an 8K context window. That is the 1.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Pruned80 Llama 3.2 3B on an 8 GB GPU?

Yes, with Q4_K_M: the 1.2 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Pruned80 Llama 3.2 3B GGUF?

It depends on the quant: Q4_0 is 0.3 GB, Q8_0 is 0.5 GB, Q4_K_M is 1.2 GB.

What context length does Pruned80 Llama 3.2 3B support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.

Where can I download Pruned80 Llama 3.2 3B GGUF?

The files are on Hugging Face in the mikepwcscaling/pruned80-Llama-3.2-3B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Pruned80 Llama 3.2 3B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from mikepwcscaling

All by mikepwcscaling →

More Llama models

All Llama →

Other tiny models

All tiny models →